Peft Python Packages

peft

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-R1, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, Phi4, ...) (AAAI 2025).

gptqmodel

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

soup-cli

Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.

mcore-bridge

MCore-Bridge: Providing Megatron-Core model definitions for state-of-the-art large models and making Megatron training as simple as Transformers — with support for 300+ large language models and 200+ multimodal large models.

mlx-tune

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

nexuss-transformer

Nexuss Transformer Framework

abliterix

Automated alignment adjustment for LLMs — direct steering, LoRA, and MoE expert-granular abliteration, optimized via multi-objective Optuna TPE.

moe-peft

An Efficient LLM Fine-Tuning Factory Optimized for MoE PEFT

llmtuner

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

document-language-model

Document-first local LLM training, preference mining, retraining, and multi-target export from .dlm docs, codebases, and multimodal sources.

anchor-vision

Python client for Anchor — PaliGemma2 multi-LoRA vision inference

lazyllm-llamafactory

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

finetunecheck

Automated base vs fine-tuned LLM comparison with forgetting detection, capability retention scoring, and visual diff reports.

xturing

Build, personalize and control your own LLMs. From data pre-processing to fine-tuning, xTuring provides an easy way to personalize open-source LLMs. Join our discord community: https://discord.gg/TgHXuSJEk6

ntf

Nexuss Transformer Framework

unsloth-mlx

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

zenith-nlp-framework

An advanced, from-scratch NLP framework for training and deploying modern transformer models.

mlora-cli

An Efficient "Factory" to Build Multiple LoRA Adapters

easylora

Batteries-included toolkit for LoRA / QLoRA fine-tuning with Hugging Face Transformers

simplifine-alpha

🚀 Easy, open-source LLM finetuning with one-line commands, seamless cloud integration, and popular optimization frameworks. ✨

aletheia-lora

Gradient-guided layer selection for efficient LoRA fine-tuning across architectures

bidora

BiDoRA/LoRA fine-tuning toolkit for 3D code generation and spatial intelligence